arXiv：cs.AI· Rui Wang, Haoyu Zhang, Ran Cheng·· 23 小时前
GeoBridge：面向几何视觉的可迁移解码器拓扑演化框架
GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision
AI 导读
GeoBridge 通过演化搜索可迁移的解码器拓扑，将残差、串行与并行组合的原始算子组织成可复用设计。一次源搜索约需 12 GPU 小时，GeoBridgeNet-A3 在 NYU Depth V2 和 KITTI 上取得四个适配解码器基线中最佳深度精度，同一拓扑在 RealEstate10K 上达到 27.11 dB PSNR，其精炼表示还支持 LERF 上的开放词汇分割。
正文
Abstract:Depth estimation and Gaussian reconstruction share a need for multi-scale feature processing, yet use different prediction interfaces and training objectives. Whether a decoder's internal computation can be optimized once and reused across these systems remains a structural design question. Search over primitive configurations alone leaves the organization of transformations fixed. To address this gap, we propose GeoBridge, an evolutionary framework for transferable decoder topologies. First, GeoBridge makes stage-internal topology searchable through residual, sequential, and parallel composition of configurable primitives. Shape-preserving composition retains the stage interfaces of a fixed multi-scale scaffold. Second, a functional-tree encoding supports stage-aware crossover and hierarchical mutation, while a gradient sensitivity-alignment proxy evaluates candidates without training. Multi-objective evolution balances this proxy with computation and parameter cost. Third, selected topologies are instantiated and trained in target systems with task-specific prediction interfaces. A single source search takes approximately 12 GPU hours. GeoBridgeNet-A3 achieves the best depth accuracy among four adapted decoder baselines under a common encoder and training protocol on NYU Depth V2 and KITTI. The same topology reaches 27.11 dB PSNR in Gaussian novel-view synthesis on RealEstate10K, and its refined representations support open-vocabulary segmentation on LERF. These results support decoder topology as a reusable design object across the evaluated geometric vision systems. Code and pretrained weights are available at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.15280 [cs.CV] |
| (or arXiv:2610.15280v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15280 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rui Wang [view email]
[v1]
Sun, 11 Oct 2026 02:23:20 UTC (11,228 KB)
来源：arXiv：cs.AI · arxiv.org